In [ ]:
# class names
class_names = sorted(os.listdir(train_dir))
# Data Distribution
train_class_counts = {class_name: len(os.listdir(os.path.join(train_dir, class_name))) for class_name in class_names}
test_class_counts = {class_name: len(os.listdir(os.path.join(test_dir, class_name))) for class_name in class_names}
print("Training Data Class Counts:")
print(train_class_counts)
print("\nTesting Data Class Counts:")
print(test_class_counts)
# Data Visualization
def plot_class_distribution(train_counts, test_counts):
labels = list(train_counts.keys())
train_values = list(train_counts.values())
test_values = list(test_counts.values())
x = np.arange(len(labels))
width = 0.35
fig, ax = plt.subplots()
rects1 = ax.bar(x - width/2, train_values, width, label='Train')
rects2 = ax.bar(x + width/2, test_values, width, label='Test')
ax.set_ylabel('Count')
ax.set_title('Class Distribution')
ax.set_xticks(x)
ax.set_xticklabels(labels)
ax.legend()
plt.show()
plot_class_distribution(train_class_counts, test_class_counts)
# Data Visualization
def plot_sample_images(directory, class_names, num_samples=5):
plt.figure(figsize=(10, 5*num_samples))
for i, class_name in enumerate(class_names):
class_dir = os.path.join(directory, class_name)
sample_images = os.listdir(class_dir)[:num_samples]
for j, image_name in enumerate(sample_images):
image_path = os.path.join(class_dir, image_name)
image = load_img(image_path, target_size=(224, 224))
plt.subplot(num_samples, len(class_names), i * num_samples + j + 1)
plt.imshow(image)
plt.title(class_name)
plt.axis("off")
plt.show()
print("\nSample Training Images:")
plot_sample_images(train_dir, class_names)
print("\nSample Testing Images:")
plot_sample_images(test_dir, class_names)
Training Data Class Counts:
{'cat': 1000, 'dog': 1000}
Testing Data Class Counts:
{'cat': 1000, 'dog': 1000}
Sample Training Images:
Sample Testing Images:
